Towards evolutionary discovery of typical clinical pathways in electronic health records

According to value-based health care, hospitals should deliver high quality and cost-effective medical treatments. Clinical pathways represent typical ways of treatment and indicate its impact on hospital resources. In this paper, we propose three approaches to discover and to cluster clinical pathways using the k-means method and genetic algorithms. A data set of 3434 electronic health records of patients with acute coronary syndrome is used to test proposed approaches. The approaches are compared with five clustering metrics. The best approach shows the best values for four of five metrics. In the future, we plan to embed the best approach of discovering clinical pathways in personalized Decision Support System of Almazov National Medical Research Centre (Saint Petersburg, Russia).